LTX-2 · unsloth

LTX-2 Q4_K_M

This file is exactly 12,840,118,752 bytes — 11.96 GiB / 12.84 GB at an effective 5.442 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 3510 tensors parsed

Get it

11.96 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/LTX-2-GGUF:Q4_K_M

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download unsloth/LTX-2-GGUF ltx-2-19b-dev-Q4_K_M.gguf
Direct download

Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.

Repository →
Size
11.96 GiB
12.84 GB
Effective bpw
5.442
from real bytes ÷ params
Tensors
3510
Header
0.29 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
2140
Q4_K
992
Q6_K
340
BF16
26
Q5_K
7
Q8_0
5

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.